Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I've churned off OAI in favor of maxing out Claude. Better coding model and less creepy engagement hacking in the chat interface.
 help



I get plenty of creepy engagement hacking with claude’s chat too now. Before memory it was better.

You can always turn it off

I want some useful memory but it seems hardcoded to try shoehorn in personal details or tidbits from past conversations into responses. Even if I specifically ask it not to in my personalization prompt.

It is interesting that both "customer support" comments here suggesting "you're just using it wrong" are from very recent accounts with very little karma.

Always, eh?



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: